© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72301
    Prev
    Next
    INDEX
    Explanations

    components.generated.decorative.inventory.adding.item

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is detect numeric tokens or sequences of digits in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lacer
    -1.08
    ekw
    -1.02
    roti
    -1.00
    leos
    -1.00
    fino
    -0.96
    ஓ
    -0.96
    manha
    -0.95
    piecz
    -0.94
    jango
    -0.93
     дописа
    -0.93
    POSITIVE LOGITS
    ry
    1.00
    ází
    0.94
    ary
    0.94
    Te
    0.92
    able
    0.91
    omics
    0.91
     costa
    0.90
    其中
    0.90
    l
    0.90
     Melayu
    0.89
    Activations Density 0.007%

    No Known Activations